© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 55638
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <?↵
    -0.08
     kode
    -0.07
    的事
    -0.07
    🕵
    -0.07
    行程
    -0.07
    /j
    -0.07
     aynı
    -0.07
    soft
    -0.07
    的良好
    -0.07
     Diy
    -0.07
    POSITIVE LOGITS
    _SURFACE
    0.07
     excitement
    0.07
    BUR
    0.07
    �
    0.07
     Rever
    0.07
     columns
    0.06
    욷
    0.06
    URRENT
    0.06
    慑
    0.06
    ﺂ
    0.06
    Activations Density 0.082%

    No Known Activations